Fix typo

Signed-off-by: David Gageot <david.gageot@docker.com>

Author: dgageot

.github/ISSUE_TEMPLATE/bug-.md

@@ -31,7 +31,7 @@ A clear and concise description of what you expected to see/happen.
 **Screenshots**  
 
 If applicable, add screenshots to help explain your problem.
-Especially useful if the problem is visual (rendering issues etc) or you're not totally sure how to explain the problem and need to show it to us
+Especially useful if the problem is visual (rendering issues etc.) or you're not totally sure how to explain the problem and need to show it to us
 
 **OS and Terminal type**  
 

docs/CONTRIBUTING.md

@@ -2,7 +2,7 @@
 
 ## Development environment setup
 
-> We currently support `cagent` development on MacOS and linux based systems. Windows support coming soon
+> We currently support `cagent` development on macOS and linux based systems. Windows support coming soon
 
 #### Build from source
 
@@ -62,14 +62,14 @@ $ task build-local
 - **Root Agent**: Main entry point that coordinates the system. This represents the first agent you interact with
 - **Sub-Agents**: Specialized agents for specific domains or tasks
 - **Tools**: External capabilities agents can use via the Model Context Protocol (MCP)
-- **Models**: Models agents can be configures to use. They include the AI provider and the model configuration (model to use, max_tokens, temperature, etc.)
+- **Models**: Models agents can be configured to use. They include the AI provider and the model configuration (model to use, max_tokens, temperature, etc.)
 
 ### Agent <-> Sub-Agent Delegation Flow
 
 1. User interacts with root agent
 2. Root agent analyzes the request
 3. Root agent can decide to delegate to appropriate sub-agent if specialized knowledge is needed
-4. Sub-agent processes the task delegated to it using its tools and expertise, in it's own agentic loop.
+4. Sub-agent processes the task delegated to it using its tools and expertise, in its own agentic loop.
 5. Results eventually flow back to the root agent and the user
 
 ## Project Architecture

docs/specs/cagent-mcp-mode/impl-progress.md

@@ -15,7 +15,7 @@
 ### Phase 1: Service Core Foundation ✅ **COMPLETE**
 
 #### 1.1 Project Setup
-- [x] **Verify MCP dependency**: Confirm `github.com/mark3labs/mcp-go v0.34.0` is available in go.mod
+- [x] **Verify MCP dependency**: Confirm `github.com/mark3labs/mcp-go v0.34.0` is available in `go.mod`
 - [x] **Create servicecore package**: Set up `pkg/servicecore/` directory structure
 - [x] **Create MCP package**: Set up `pkg/mcpserver/` directory
 - [x] **Add command structure**: Create skeleton for `cmd/root/mcp.go`

examples/bio.yaml

@@ -17,7 +17,7 @@ agents:
       **Tasks:**
       1. **Search for User Information**: Use web searches to find relevant information about the user.
       2. **Fetch Additional Data**: Use the Fetch tool to gather more specific information from targeted sources.
-      3. **On errors**, search for other sources and repeat fron step 2.
+      3. **On errors**, search for other sources and repeat from step 2.
       4. **Compile Biography**: Combine the gathered information into a coherent biography.
       5. **Verify the credibility of sources** before including information.
 

examples/blog.yaml

@@ -4,7 +4,7 @@ version: "1"
 agents:
   root:
     model: anthropic
-    description: Writes techincal blog posts
+    description: Writes technical blog posts
     instruction: |
       You are the leader of a team of AI agents for a technical blog writing workflow.
 
@@ -17,7 +17,7 @@ agents:
       <WORKFLOW>
         1. Call the `web_search_agent` agent to search for the web to get important information about the task that is asked
 
-        3. Call the `writer` agent to write a 750-word technical blog post based on the reserach done by the web_search_agent
+        3. Call the `writer` agent to write a 750-word technical blog post based on the research done by the web_search_agent
       </WORKFLOW>
 
       - Use the transfer_to_agent tool to call the right agent at the right time to complete the workflow.

internal/creator/instructions.txt

@@ -33,7 +33,7 @@ agent_name:
 
 Here is the list of the available builtin tools an agent can use, each of them is optional
 
-- `-type: shell`: Gives the agent access to a shell where it can run commands on the users's computer
+- `-type: shell`: Gives the agent access to a shell where it can run commands on the users' computer
 - `-type: filesystem`: Gives the agent access to the filesystem for reading, writing files etc.
 - `-type: script`: Gives the agent access to custom shell commands/scripts with predefined parameters and environment variables
 - `-type: todo`: Gives the agent tools for tracking todo items it needs to finish in order to complete the task for the user. Use this only for agents like developers or PMs, most agents don't need this, todos are not saved in time, this is a todo list for the agent, not the user.
@@ -98,11 +98,11 @@ agents:
                 DOCKER_BUILDKIT: "1"
             list_repos:
               cmd: "curl -s https://api.github.com/users/$username/repos | jq '.[].name'"
-              description: "List Github repositories for a user"
+              description: "List GitHub repositories for a user"
               args:
                 username:
                   type: string
-                  description: "Github username to get repositories for"
+                  description: "GitHub username to get repositories for"
               required: ["username"]
 ```
 

pkg/desktop/login.go

@@ -13,7 +13,7 @@ type DockerHubInfo struct {
 
 func GetToken(ctx context.Context) string {
 	// Allow the user to override the token via an environment variable.
-	// This is e.g useful when talking to a gateway on staging.
+	// This is e.g. useful when talking to a gateway on staging.
 	manualToken := os.Getenv("DOCKER_TOKEN")
 	if manualToken != "" {
 		return manualToken